ENTITY
Soft-GCG
Soft-GCG
PulseAugur coverage of Soft-GCG — every cluster mentioning Soft-GCG across labs, papers, and developer communities, ranked by signal.
Total · 30d
2
2 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
2
2 over 90d
TIER MIX · 90D
TOPICS
RECENT · PAGE 1/1 · 2 TOTAL
-
New research probes and breaks LLM safety mechanisms
Researchers have developed new methods to probe and potentially break the safety mechanisms in large language models. By using activation-guided adversarial suffixes, they found that safety representations are distribut…
-
New methods probe and break LLM safety representations
Researchers have developed new methods to probe and potentially break the safety mechanisms within large language models. By analyzing how models refuse certain prompts, they identified that safety representations are d…